Land use change detection for environmental management : using multi-temporal, satellite data in the Apodi Valley of northeastern Brazil

In this study maximum-likelihood, supervised classification along with post-classification change detection was applied to satellite images for 1986, 1989, 1996, 2001, and 2009, in order to map land-cover changes within the Apodi Valley region of northeastern Brazil. The supervised classification was carried out on the six reflective bands and ground truthed. The classification results were then further refined using ancillary data, visual interpretation and expert knowledge of the area along with GIS. Post-classification change detection then generated a change image in the form of cross-tabulations. Fifteen land cover classes existed within the area, and reclamation processes during the 1990's changed them substantially, with conflicting changes being caused primarily by lack of both stability and consistency in the government's land use policies. The result was extensive vegetation degradation and water logging in parts of the study area.